GIS equipment discharge type determination method and device, electronic equipment and storage medium

By extracting time-frequency domain features and comparing similarity of the discharge noise waveform of GIS equipment, the problem of inaccurate discharge type analysis of GIS equipment is solved, and more accurate and reliable discharge type identification is achieved.

CN118962349AActive Publication Date: 2024-11-15BAODING HUACHUANG ELECTRIC
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411019575.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-15
Estimated Expiration
2044-07-29

AI Technical Summary

Technical Problem

In existing technologies, the analysis results of discharge types of GIS equipment are inaccurate. This is due to limitations in the probability of discharge occurrence and the difficulty in obtaining a large number of samples, which leads to inaccurate analysis results.

Method used

By acquiring the discharge noise waveform, time-frequency domain features are extracted, a time-frequency domain matrix is ​​constructed, frequency domain vectors are extracted, and a similarity comparison is performed with a standard frequency domain vector set to determine the discharge type.

Benefits of technology

This improves the accuracy and reliability of discharge type analysis for GIS equipment, reduces dependence on sample size, and enhances the credibility of analysis results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118962349A_ABST
    Figure CN118962349A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of GIS equipment abnormity diagnosis, in particular to a GIS equipment discharge type determination method and device, electronic equipment and a storage medium. Performing time-frequency domain feature extraction on the discharge noise waveform to obtain a time-frequency domain matrix; extracting a plurality of frequency domain vectors from the time-frequency domain matrix, and constructing a plurality of discharge type queues according to a standard frequency domain vector set and the plurality of frequency domain vectors; and finally, according to the plurality of discharge type queues, determining probabilities of a plurality of discharge types, and according to the probabilities of the plurality of discharge types, determining a discharge type of the discharge noise waveform. According to the method, the time-frequency domain matrix of the discharge noise waveform is extracted, the frequency domain vector is extracted from the time-frequency domain matrix and is subjected to similarity comparison with the standard frequency domain vector set, the discharge type is determined according to the comparison result, and the discharge type analysis result is more accurate and reliable.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of GIS equipment abnormality diagnosis, and in particular to a method, device, electronic device and storage medium for determining a discharge type of GIS equipment. Background Art

[0002] Gas Insulated Switch (GIS) is composed of circuit breakers, disconnectors, earthing switches, current transformers, voltage transformers, lightning arresters, busbars, connectors and outgoing line terminals. These devices or components are all enclosed in a metal grounded casing, which is filled with insulating gas (usually SF6) at a certain pressure, so it is also called insulated gas fully enclosed combination electrical equipment.

[0003] GIS is a high-voltage electrical equipment with high operating reliability, low maintenance workload and long maintenance cycle. Its failure rate is only 20% to 40% of conventional equipment, but GIS also has its inherent disadvantages. Due to the leakage of SF6 gas, the infiltration of external moisture, the presence of conductive impurities, the aging of insulators and other factors, it may cause internal flashover failure of GIS. The fully sealed structure of GIS makes it difficult to locate and repair the fault, and the maintenance work is complicated. The average power outage maintenance time after the accident is longer than that of conventional equipment, and its power outage range is large, often involving many non-faulty components.

[0004] In some related technologies, ultrasonic detection devices are installed on GIS equipment to extract the noise waveform generated when discharge occurs. The time and location of the discharge can be roughly inferred from the noise waveform. In some technologies, the type of discharge is determined by artificial intelligence algorithms after processing the noise waveform. These artificial intelligence algorithms usually require a large number of samples to achieve a good analysis effect. However, due to the possibility of discharge, it is not easy to obtain a large number of samples. Therefore, the analysis results of the discharge type of GIS equipment in the prior art are not accurate.

[0005] Based on this, it is necessary to develop and design a method for determining the discharge type of GIS equipment. Summary of the invention

[0006] The embodiments of the present invention provide a method, device, electronic device and storage medium for determining the discharge type of GIS equipment, which are used to solve the problem of inaccurate analysis results of the discharge type of GIS equipment in the prior art.

[0007] In a first aspect, an embodiment of the present invention provides a method for determining a discharge type of a GIS device, comprising:

[0008] Obtain discharge noise waveform;

[0009] Extracting time-frequency domain features of the discharge noise waveform to obtain a time-frequency domain matrix;

[0010] Extracting multiple frequency domain vectors from the time-frequency domain matrix, and constructing multiple discharge type queues according to a standard frequency domain vector set and the multiple frequency domain vectors, wherein the standard frequency domain vector set represents the discharge types corresponding to the multiple standard frequency domain vectors;

[0011] The probabilities of a plurality of discharge types are determined according to the plurality of discharge type queues, and the discharge type of the discharge noise waveform is determined according to the probabilities of the plurality of discharge types.

[0012] In a possible implementation, extracting the time-frequency domain features of the discharge noise waveform to obtain a time-frequency domain matrix includes:

[0013] discretizing the discharge noise waveform to obtain a discharge data set;

[0014] Get multiple characteristic frequencies;

[0015] From the plurality of characteristic frequencies, sequentially taking characteristic frequencies as frequencies to be processed;

[0016] Slip-taking a plurality of data segments from the discharge data set;

[0017] Extracting frequency domain features from the multiple data segments according to the frequencies to be processed to obtain multiple frequency domain features, wherein each frequency domain feature corresponds to one data segment;

[0018] constructing the plurality of frequency domain features into a frequency domain feature vector according to the positions of the plurality of data segments in the discharge data set;

[0019] Adding the eigenvector frequency domain eigenvector to the time-frequency domain matrix;

[0020] If the traversal of the multiple characteristic frequencies is not completed, the process jumps to the step of sequentially taking out characteristic frequencies from the multiple characteristic frequencies as frequencies to be processed.

[0021] In a possible implementation, the extracting frequency domain features of the multiple data segments according to the to-be-processed frequencies to obtain multiple frequency domain features includes:

[0022] Frequency domain features are extracted from the multiple data segments according to the first formula and the frequency to be processed to obtain multiple frequency domain features, wherein the first formula is:

[0023]

[0024] Where DF(n) is the nth frequency domain feature, Dnmax is the total number of data in the first data segment, and DS n(Dn) is the Dn+1th data of the nth data segment, e is a natural constant, j is an imaginary unit, ω is the frequency to be processed, Tn is the number of data in the data segment within the period corresponding to the frequency to be processed, and π is the ratio of circumference to circumference.

[0025] In a possible implementation, multiple frequency domain vectors are extracted from the time-frequency domain matrix, and multiple discharge type queues are constructed according to a standard frequency domain vector set and the multiple frequency domain vectors, wherein the standard frequency domain vector set represents the discharge types corresponding to the multiple standard frequency domain vectors, including:

[0026] Acquire multiple standard frequency domain vector sets, wherein each standard frequency domain vector set corresponds to a frequency domain frequency, the standard frequency domain vector set includes a first weight vector and multiple standard frequency domain vectors, and each standard frequency domain vector corresponds to a discharge type;

[0027] The frequency domain vectors are traversally extracted from the time-frequency domain matrix as the frequency domain vectors to be processed, and the following steps are performed after each extraction:

[0028] Extracting a target standard frequency domain vector set from the plurality of standard frequency domain vector sets according to the frequency domain frequency of the frequency domain vector to be processed;

[0029] Using a target weight vector to perform weighting processing on the frequency domain vector to be processed to obtain an intermediate frequency domain vector, wherein the target weight vector is the first weight vector in the target standard frequency domain vector set;

[0030] According to the second formula, a similarity coefficient between the intermediate frequency domain vector and each candidate standard frequency domain vector is determined, thereby obtaining multiple similarity coefficients, wherein the candidate standard frequency domain vector is a standard frequency domain vector in the target standard frequency domain vector set, and the second formula is:

[0031]

[0032] Where SML is the similarity coefficient, MDF(n) is the nth element of the intermediate frequency domain vector, SDF(n) is the nth element of the target standard frequency domain vector, and nmax is the total number of elements in the intermediate frequency domain vector;

[0033] According to the discharge type of the candidate standard frequency domain vector, the multiple similarity coefficients are respectively added to the corresponding multiple discharge type queues, wherein each discharge type queue corresponds to one discharge type.

[0034] In a possible implementation, the process of constructing the standard frequency domain vector set includes:

[0035] Obtaining an intermediate weight vector and a plurality of sample frequency domain vectors, wherein each sample frequency domain vector corresponds to a discharge type;

[0036] Clustering the plurality of sample frequency domain vectors into a plurality of sample classes as many as the number of discharge types;

[0037] The discharge type of the majority vector in each sample class is taken as the cluster discharge type;

[0038] Calculating the class centers of the multiple sample classes respectively to obtain multiple sample class centers;

[0039] Extracting heterogeneous vectors from each sample class, thereby obtaining a plurality of heterogeneous vectors, wherein the heterogeneous vectors are sample frequency domain vectors whose discharge type is different from the cluster discharge type of the class to which they belong;

[0040] If the ratio of the number of the plurality of heterogeneous vectors to the number of the plurality of sample frequency domain vectors is greater than the heterogeneous number ratio threshold, the intermediate weight vector is adjusted according to the plurality of heterogeneous vectors, each sample frequency domain vector is weighted by using the adjusted intermediate weight vector, the sample frequency domain vector after weighting is used as the sample frequency domain vector, and the process jumps to the step of clustering the plurality of sample frequency domain vectors into a plurality of sample classes of the number of discharge types;

[0041] Otherwise, the multiple target centers are used as the multiple standard frequency domain vectors, the intermediate weight vector is used as the first weight vector, and a standard frequency domain vector set is constructed using the first weight vector and the multiple standard frequency domain vectors.

[0042] In a possible implementation, adjusting the intermediate weight vector according to the multiple heterogeneous vectors and performing weighting processing on each sample frequency domain vector using the adjusted intermediate weight vector includes:

[0043] According to the discharge type of each heterogeneous vector, a sample class center is selected from the multiple sample class centers as a target center, thereby obtaining multiple target centers, wherein the cluster discharge type of the source class of the target center is the same as the discharge type of the heterogeneous vector;

[0044] A weight optimization equation is constructed according to the multiple heterogeneous vectors and the multiple sample class centers, wherein the weight optimization equation is:

[0045]

[0046] In the formula, SSDF i (n) is the nth element of the ith heterogeneous vector, CDF i (n) is the nth element of the target center of the i-th heterogeneous vector, and W(n) is the nth element of the intermediate weight vector;

[0047] According to the weight optimization equation, adjusting the intermediate weight vector;

[0048] Each sample frequency domain vector is weighted using the adjusted intermediate weight vector.

[0049] In a possible implementation, determining the probabilities of multiple discharge types according to the multiple discharge type queues, and determining the discharge type of the discharge noise waveform according to the probabilities of the multiple discharge types includes:

[0050] Calculate the sum of multiple data in each discharge type queue, thereby obtaining multiple queue sums;

[0051] According to the third formula and the sum of the multiple queues, multiple discharge probabilities are determined, wherein each discharge probability represents the probability of a discharge type, and the third formula is:

[0052]

[0053] Where P(k) is the probability of the kth discharge type, R(k) is the queue sum of the kth discharge queue, and cnmax is the total number of discharge types;

[0054] The discharge type corresponding to the discharge probability with the largest value is used as the discharge type of the discharge noise waveform.

[0055] In a second aspect, an embodiment of the present invention provides a GIS equipment discharge type determination device, which is used to implement the GIS equipment discharge type determination method described in the first aspect or any possible implementation of the first aspect, wherein the GIS equipment discharge type determination device includes:

[0056] A discharge noise waveform acquisition module, used to acquire a discharge noise waveform;

[0057] A time-frequency domain feature extraction module, used to extract the time-frequency domain features of the discharge noise waveform to obtain a time-frequency domain matrix;

[0058] A discharge type queue construction module is used to extract multiple frequency domain vectors from the time-frequency domain matrix, and construct multiple discharge type queues according to a standard frequency domain vector set and the multiple frequency domain vectors, wherein the standard frequency domain vector set represents the discharge types corresponding to the multiple standard frequency domain vectors;

[0059] as well as,

[0060] The discharge type determination module is used to determine the probabilities of multiple discharge types according to the multiple discharge type queues, and determine the discharge type of the discharge noise waveform according to the probabilities of the multiple discharge types.

[0061] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the steps of the method described in the first aspect or any possible implementation method of the first aspect.

[0062] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0063] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0064] The embodiment of the present invention discloses a method for determining the discharge type of GIS equipment, which first obtains a discharge noise waveform; then extracts time-frequency domain features of the discharge noise waveform to obtain a time-frequency domain matrix; then extracts multiple frequency domain vectors from the time-frequency domain matrix, and constructs multiple discharge type queues according to a standard frequency domain vector set and the multiple frequency domain vectors, wherein the standard frequency domain vector set represents the discharge types corresponding to the multiple standard frequency domain vectors; finally, according to the multiple discharge type queues, the probabilities of the multiple discharge types are determined, and according to the probabilities of the multiple discharge types, the discharge type of the discharge noise waveform is determined. The embodiment of the present invention extracts the time-frequency domain matrix of the discharge noise waveform, extracts the frequency domain vector from the time-frequency domain matrix, and compares the similarity with the standard frequency domain vector set, and determines the discharge type according to the comparison result. The standard frequency domain vector set requires fewer samples. Since the discharge type is determined by comparison with the standard samples, the discharge type analysis result is more accurate and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0066] Figure 1 is a flow chart of a method for determining a discharge type of GIS equipment provided by an embodiment of the present invention;

[0067] Figure 2 It is a principle diagram of a process of extracting frequency domain features by slidingly taking out multiple data segments from a discharge data set provided by an embodiment of the present invention;

[0068] Figure 3It is a schematic diagram of extracting heterogeneous vectors by clustering multiple sample frequency domain vectors provided by an embodiment of the present invention;

[0069] Figure 4 It is a functional block diagram of a device for determining a discharge type of GIS equipment provided in an embodiment of the present invention;

[0070] Figure 5 It is a functional block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0071] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, and methods are omitted so as not to obscure the description of the present invention with unnecessary details.

[0072] In order to make the purpose, technical solutions and advantages of the present invention more clear, a specific implementation method will be described below in conjunction with the accompanying drawings.

[0073] The following is a detailed description of an embodiment of the present invention. This example is implemented based on the technical solution of the present invention, and provides a detailed implementation method and a specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0074] Figure 1 A flow chart of a method for determining a discharge type of GIS equipment provided in an embodiment of the present invention.

[0075] like Figure 1 As shown, it shows a flowchart of the method for determining the discharge type of GIS equipment provided by an embodiment of the present invention, which is described in detail as follows:

[0076] In step 101, a discharge noise waveform is obtained.

[0077] In step 102, time-frequency domain feature extraction is performed on the discharge noise waveform to obtain a time-frequency domain matrix.

[0078] In some implementations, step 102 includes:

[0079] discretizing the discharge noise waveform to obtain a discharge data set;

[0080] Get multiple characteristic frequencies;

[0081] From the plurality of characteristic frequencies, sequentially taking characteristic frequencies as frequencies to be processed;

[0082] Slip-taking a plurality of data segments from the discharge data set;

[0083] Extracting frequency domain features from the multiple data segments according to the frequencies to be processed to obtain multiple frequency domain features, wherein each frequency domain feature corresponds to one data segment;

[0084] constructing the plurality of frequency domain features into a frequency domain feature vector according to the positions of the plurality of data segments in the discharge data set;

[0085] Adding the eigenvector frequency domain eigenvector to the time-frequency domain matrix;

[0086] If the traversal of the multiple characteristic frequencies is not completed, jump to the step of sequentially taking out characteristic frequencies from the multiple characteristic frequencies as the frequencies to be processed.

[0087] In some implementations, extracting frequency domain features from the multiple data segments according to the frequencies to be processed to obtain multiple frequency domain features includes:

[0088] Frequency domain features are extracted from the multiple data segments according to the first formula and the frequency to be processed to obtain multiple frequency domain features, wherein the first formula is:

[0089]

[0090] Where DF(n) is the nth frequency domain feature, Dnmax is the total number of data in the first data segment, and DS n (Dn) is the Dn+1th data of the nth data segment, e is a natural constant, j is an imaginary unit, ω is the frequency to be processed, Tn is the number of data in the data segment within the period corresponding to the frequency to be processed, and π is the ratio of circumference to circumference.

[0091] Exemplarily, in the embodiment of the present invention, a time-frequency domain matrix is ​​extracted based on the discharge noise waveform collected by the GIS device. Then, a frequency domain vector is extracted from the time-frequency domain matrix, and these extracted frequency vectors are compared with the standard frequency vectors for similarity, and the obtained similarity values ​​are added to the discharge type queue of the standard frequency vector. According to the discharge type queue, the probability of each discharge type is calculated, and the discharge type is determined according to the probability of the discharge type.

[0092] like Figure 2As shown, the figure shows a schematic diagram of the process of extracting frequency domain features by slidingly taking out multiple data segments from a discharge data set provided by an embodiment of the present invention. In terms of time-frequency domain matrix construction, the embodiment of the present invention first extracts data segments 202 from a discharge data set 201 (the discharge data set is obtained by discretizing the discharge noise waveform) by sliding, and frequency domain features 203 are extracted from each data segment 202 respectively. According to the position of the data segment 202, the frequency domain features 203 are constructed into frequency domain feature vectors 204, and finally, multiple frequency domain vectors 204 in different frequency domains are constructed into a time-frequency domain matrix.

[0093] In terms of frequency domain feature extraction, the embodiment of the present invention uses the first method, and the first formula is:

[0094]

[0095] Where DF(n) is the nth frequency domain feature, Dnmax is the total number of data in the first data segment, and DS n (Dn) is the Dn+1th data of the nth data segment, e is a natural constant, j is an imaginary unit, ω is the frequency to be processed, Tn is the number of data in the data segment within the period corresponding to the frequency to be processed, and π is the ratio of circumference to circumference.

[0096] In step 103, multiple frequency domain vectors are extracted from the time-frequency domain matrix, and multiple discharge type queues are constructed according to a standard frequency domain vector set and the multiple frequency domain vectors, wherein the standard frequency domain vector set represents the discharge types corresponding to the multiple standard frequency domain vectors.

[0097] In some implementations, step 103 includes:

[0098] The step of comparing the time-frequency domain matrix with multiple sample time-frequency domain matrices to extract multiple components includes:

[0099] Acquire multiple standard frequency domain vector sets, wherein each standard frequency domain vector set corresponds to a frequency domain frequency, the standard frequency domain vector set includes a first weight vector and multiple standard frequency domain vectors, and each standard frequency domain vector corresponds to a discharge type;

[0100] The frequency domain vectors are traversally extracted from the time-frequency domain matrix as the frequency domain vectors to be processed, and the following steps are performed after each extraction:

[0101] Extracting a target standard frequency domain vector set from the plurality of standard frequency domain vector sets according to the frequency domain frequency of the frequency domain vector to be processed;

[0102] Using a target weight vector to perform weighting processing on the frequency domain vector to be processed to obtain an intermediate frequency domain vector, wherein the target weight vector is the first weight vector in the target standard frequency domain vector set;

[0103] According to the second formula, a similarity coefficient between the intermediate frequency domain vector and each candidate standard frequency domain vector is determined, thereby obtaining multiple similarity coefficients, wherein the candidate standard frequency domain vector is a standard frequency domain vector in the target standard frequency domain vector set, and the second formula is:

[0104]

[0105] Where SML is the similarity coefficient, MDF(n) is the nth element of the intermediate frequency domain vector, SDF(n) is the nth element of the target standard frequency domain vector, and nmax is the total number of elements in the intermediate frequency domain vector;

[0106] According to the discharge type of the candidate standard frequency domain vector, the multiple similarity coefficients are respectively added to the corresponding multiple discharge type queues, wherein each discharge type queue corresponds to one discharge type.

[0107] In some implementations, the process of constructing the standard frequency domain vector set includes:

[0108] Obtaining an intermediate weight vector and a plurality of sample frequency domain vectors, wherein each sample frequency domain vector corresponds to a discharge type;

[0109] Clustering the plurality of sample frequency domain vectors into a plurality of sample classes as many as the number of discharge types;

[0110] The discharge type of the majority vector in each sample class is taken as the cluster discharge type;

[0111] Calculating the class centers of the multiple sample classes respectively to obtain multiple sample class centers;

[0112] Extracting heterogeneous vectors from each sample class, thereby obtaining a plurality of heterogeneous vectors, wherein the heterogeneous vectors are sample frequency domain vectors whose discharge type is different from the cluster discharge type of the class to which they belong;

[0113] If the ratio of the number of the plurality of heterogeneous vectors to the number of the plurality of sample frequency domain vectors is greater than the heterogeneous number ratio threshold, the intermediate weight vector is adjusted according to the plurality of heterogeneous vectors, each sample frequency domain vector is weighted by using the adjusted intermediate weight vector, the sample frequency domain vector after weighting is used as the sample frequency domain vector, and the process jumps to the step of clustering the plurality of sample frequency domain vectors into a plurality of sample classes of the number of discharge types;

[0114] Otherwise, the multiple target centers are used as the multiple standard frequency domain vectors, the intermediate weight vector is used as the first weight vector, and a standard frequency domain vector set is constructed using the first weight vector and the multiple standard frequency domain vectors.

[0115] In some implementations, adjusting the intermediate weight vector according to the multiple heterogeneous vectors and performing weighting processing on each sample frequency domain vector using the adjusted intermediate weight vector includes:

[0116] According to the discharge type of each heterogeneous vector, a sample class center is selected from the multiple sample class centers as a target center, thereby obtaining multiple target centers, wherein the cluster discharge type of the source class of the target center is the same as the discharge type of the heterogeneous vector;

[0117] A weight optimization equation is constructed according to the multiple heterogeneous vectors and the multiple sample class centers, wherein the weight optimization equation is:

[0118]

[0119] In the formula, SSDF i (n) is the nth element of the ith heterogeneous vector, CDF i (n) is the nth element of the target center of the i-th heterogeneous vector, and W(n) is the nth element of the intermediate weight vector;

[0120] According to the weight optimization equation, adjusting the intermediate weight vector;

[0121] Each sample frequency domain vector is weighted using the adjusted intermediate weight vector.

[0122] Exemplarily, in an embodiment of the present invention, a discharge type queue is constructed by extracting a frequency domain vector from a time-frequency domain matrix and performing similarity comparison with a standard frequency domain vector in a standard frequency domain vector set.

[0123] Specifically, the standard frequency domain vector set includes a first weight vector and multiple standard frequency domain vectors. The first weight vector is used to process the frequency domain vector extracted from the time-frequency domain matrix. In other words, the extracted frequency domain vector is weighted to obtain an intermediate frequency domain vector. One weighting method is to use the following formula:

[0124] MDF(n)=W(n)·DF(n)

[0125] Where MDF(n) is the nth element of the intermediate frequency domain vector, W(n) is the nth element of the first weight vector, and DF(n) is the nth element of the frequency domain vector extracted from the time-frequency domain matrix.

[0126] The obtained intermediate frequency domain vector is similar to each standard frequency domain vector. The implementation method of this aspect applies the second formula:

[0127]

[0128] Where SML is the similarity coefficient, MDF(n) is the nth element of the intermediate frequency domain vector, SDF(n) is the nth element of the target standard frequency domain vector, and nmax is the total number of elements in the intermediate frequency domain vector.

[0129] Finally, according to the discharge type of the standard frequency domain vector, the similarity coefficient obtained by the second formula is added to the discharge type queue.

[0130] Here we have to explain the construction process of the standard frequency domain vector set. The standard frequency domain vector is constructed based on multiple sample frequency domain vectors. First, the sample frequency domain vectors are clustered according to the number of types of discharge. If there are many heterogeneous vectors in these classes, it is necessary to adjust the sample frequency domain vectors through the intermediate weight vector. After the adjustment, the above clustering process is repeated until the number of heterogeneous vectors reaches an acceptable level. At this time, the class center of the clustered class is calculated, and the class center is used as the standard frequency domain vector, and the intermediate weight vector used to adjust the sample frequency domain vector is used as the first weight vector.

[0131] Figure 3 Schematic diagram of extracting heterogeneous vectors by clustering multiple sample frequency domain vectors provided in an embodiment of the present invention. In the figure, multiple sample frequency domain vectors 302 correspond to a discharge type respectively. For example, a square is a first discharge type, a rectangle is a second discharge type, and a circle is a third discharge type. After these sample frequency domain vectors 302 are clustered, some vectors different from most discharge types will appear in each class 301. These vectors are heterogeneous vectors 303.

[0132] These heterogeneous vectors need to be optimized through intermediate weights so that they can be clustered into the class they belong to (for example, Figure 3 Outlier vectors in the rightmost class should be adjusted to the leftmost class).

[0133] The intermediate weight vector is determined based on the class center of the class to which the heterogeneous vector should belong and the heterogeneous vector itself. One way to adjust the intermediate weight is to use the weight optimization equation:

[0134]

[0135] In the formula, SSDF i (n) is the nth element of the ith heterogeneous vector, CDF i (n) is the nth element of the target center of the i-th heterogeneous vector, and W(n) is the nth element of the intermediate weight vector.

[0136] After the intermediate weight vector is adjusted, the intermediate weight vector is used to weight each sample frequency domain vector (the aforementioned weight processing formula can be used). After the processing is completed, the clustering process is repeated. After several iterations of the above process, the number of heterogeneous vectors reaches an acceptable level. The class center can be used as the standard frequency domain vector, the class discharge type as the discharge type of the standard frequency domain vector, and the intermediate weight vector as the first weight vector. The first weight vector and multiple standard frequency domain vectors are used to construct a standard frequency domain vector set.

[0137] In step 104, the probabilities of a plurality of discharge types are determined according to the plurality of discharge type queues, and the discharge type of the discharge noise waveform is determined according to the probabilities of the plurality of discharge types.

[0138] In some implementations, step 104 includes:

[0139] Calculate the sum of multiple data in each discharge type queue, thereby obtaining multiple queue sums;

[0140] According to the third formula and the sum of the multiple queues, multiple discharge probabilities are determined, wherein each discharge probability represents the probability of a discharge type, and the third formula is:

[0141]

[0142] Where P(k) is the probability of the kth discharge type, R(k) is the queue sum of the kth discharge queue, and cnmax is the total number of discharge types;

[0143] The discharge type corresponding to the discharge probability with the largest value is used as the discharge type of the discharge noise waveform.

[0144] Exemplarily, the data in each discharge type queue is summed, and the obtained sum represents the correlation of the discharge noise waveform. The embodiment of the present invention also calculates the probability of the discharge type through these sums, and applies the third formula:

[0145]

[0146] Where P(k) is the probability of the kth discharge type, R(k) is the queue sum of the kth discharge queue, and cnmax is the total number of discharge types.

[0147] Usually, the discharge type with the largest value is selected from the above-mentioned discharge type probabilities as the discharge type of the discharge noise waveform.

[0148] The embodiment of the method for determining the discharge type of GIS equipment of the present invention first obtains the discharge noise waveform; then extracts the time-frequency domain features of the discharge noise waveform to obtain a time-frequency domain matrix; then extracts multiple frequency domain vectors from the time-frequency domain matrix, and constructs multiple discharge type queues according to the standard frequency domain vector set and the multiple frequency domain vectors, wherein the standard frequency domain vector set represents the discharge types corresponding to the multiple standard frequency domain vectors; finally, according to the multiple discharge type queues, the probabilities of the multiple discharge types are determined, and according to the probabilities of the multiple discharge types, the discharge type of the discharge noise waveform is determined. The embodiment of the present invention extracts the time-frequency domain matrix of the discharge noise waveform, extracts the frequency domain vector from the time-frequency domain matrix, and compares the similarity with the standard frequency domain vector set, and determines the discharge type according to the comparison result. The standard frequency domain vector set requires fewer samples. Since the discharge type is determined by comparison with the standard samples, the discharge type analysis result is more accurate and reliable.

[0149] It should be understood that the size of the serial numbers of the steps in the above implementation does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation method of the present invention.

[0150] The following is an implementation of the device of the present invention. For details not described in detail, reference may be made to the corresponding method implementation described above.

[0151] Figure 4 is a functional block diagram of a device for determining a discharge type of GIS equipment provided by an embodiment of the present invention, referring to Figure 4 The GIS equipment discharge type determination device includes: a discharge noise waveform acquisition module 401, a time-frequency domain feature extraction module 402, a discharge type queue construction module 403 and a discharge type determination module 404, wherein:

[0152] A discharge noise waveform acquisition module 401 is used to acquire a discharge noise waveform;

[0153] A time-frequency domain feature extraction module 402 is used to extract the time-frequency domain features of the discharge noise waveform to obtain a time-frequency domain matrix;

[0154] A discharge type queue construction module 403 is used to extract multiple frequency domain vectors from the time-frequency domain matrix, and construct multiple discharge type queues according to a standard frequency domain vector set and the multiple frequency domain vectors, wherein the standard frequency domain vector set represents the discharge types corresponding to the multiple standard frequency domain vectors;

[0155] The discharge type determination module 404 is configured to determine the probabilities of a plurality of discharge types according to the plurality of discharge type queues, and determine the discharge type of the discharge noise waveform according to the probabilities of the plurality of discharge types.

[0156] Figure 5 is a functional block diagram of an electronic device provided by an embodiment of the present invention. Figure 5 As shown, the electronic device 5 of this embodiment includes: a processor 500 and a memory 501, wherein the memory 501 stores a computer program 502 that can be run on the processor 500. When the processor 500 executes the computer program 502, the steps in the above-mentioned methods for determining the discharge type of GIS equipment and the embodiments are implemented, for example Figure 1 Steps 101 to 104 are shown.

[0157] Exemplarily, the computer program 502 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 501 and executed by the processor 500 to implement the present invention.

[0158] The electronic device 5 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 5 may include, but is not limited to, a processor 500 and a memory 501. Those skilled in the art will appreciate that Figure 5 It is only an example of the electronic device 5 and does not constitute a limitation of the electronic device 5. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 5 may also include input and output devices, network access devices, buses, etc.

[0159] The processor 500 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0160] The memory 501 may be an internal storage unit of the electronic device 5, such as a hard disk or memory of the electronic device 5. The memory 501 may also be an external storage device of the electronic device 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 5. Further, the memory 501 may also include both an internal storage unit of the electronic device 5 and an external storage device. The memory 501 is used to store the computer program 502 and other programs and data required by the electronic device 5. The memory 501 may also be used to temporarily store data that has been output or is to be output.

[0161] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the implementation method can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method implementation method, which will not be repeated here.

[0162] In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0163] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0164] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0165] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0166] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0167] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned implementation method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various methods and device implementation methods. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0168] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for determining the discharge type of GIS equipment, characterized in that: include: Obtain discharge noise waveform; Extracting time-frequency domain features of the discharge noise waveform to obtain a time-frequency domain matrix; Extracting multiple frequency domain vectors from the time-frequency domain matrix, and constructing multiple discharge type queues according to a standard frequency domain vector set and the multiple frequency domain vectors, wherein the standard frequency domain vector set represents the discharge types corresponding to the multiple standard frequency domain vectors; The probabilities of a plurality of discharge types are determined according to the plurality of discharge type queues, and the discharge type of the discharge noise waveform is determined according to the probabilities of the plurality of discharge types.

2. The method for determining the discharge type of GIS equipment according to claim 1, characterized in that: The step of extracting time-frequency domain features of the discharge noise waveform to obtain a time-frequency domain matrix includes: discretizing the discharge noise waveform to obtain a discharge data set; Get multiple characteristic frequencies; From the plurality of characteristic frequencies, sequentially taking characteristic frequencies as frequencies to be processed; Slip-taking a plurality of data segments from the discharge data set; Extracting frequency domain features from the multiple data segments according to the frequencies to be processed to obtain multiple frequency domain features, wherein each frequency domain feature corresponds to one data segment; constructing the plurality of frequency domain features into a frequency domain feature vector according to the positions of the plurality of data segments in the discharge data set; Adding the eigenvector frequency domain eigenvector to the time-frequency domain matrix; If the traversal of the multiple characteristic frequencies is not completed, the process jumps to the step of sequentially taking out characteristic frequencies from the multiple characteristic frequencies as frequencies to be processed.

3. The method for determining the discharge type of GIS equipment according to claim 2, characterized in that: The extracting frequency domain features of the multiple data segments according to the frequencies to be processed to obtain multiple frequency domain features includes: Frequency domain features are extracted from the multiple data segments according to the first formula and the frequency to be processed to obtain multiple frequency domain features, wherein the first formula is: Where DF(n) is the nth frequency domain feature, Dnmax is the total number of data in the first data segment, and DS n (Dn) is the Dn+1th data of the nth data segment, e is a natural constant, j is an imaginary unit, ω is the frequency to be processed, Tn is the number of data in the data segment within the period corresponding to the frequency to be processed, and π is the ratio of circumference to circumference.

4. The method for determining the discharge type of GIS equipment according to claim 1, characterized in that: The step of extracting multiple frequency domain vectors from the time-frequency domain matrix and constructing multiple discharge type queues according to a standard frequency domain vector set and the multiple frequency domain vectors, wherein the standard frequency domain vector set represents the discharge types corresponding to the multiple standard frequency domain vectors, including: Acquire multiple standard frequency domain vector sets, wherein each standard frequency domain vector set corresponds to a frequency domain frequency, the standard frequency domain vector set includes a first weight vector and multiple standard frequency domain vectors, and each standard frequency domain vector corresponds to a discharge type; The frequency domain vectors are traversally extracted from the time-frequency domain matrix as the frequency domain vectors to be processed, and the following steps are performed after each extraction: Extracting a target standard frequency domain vector set from the plurality of standard frequency domain vector sets according to the frequency domain frequency of the frequency domain vector to be processed; Using a target weight vector to perform weighting processing on the frequency domain vector to be processed to obtain an intermediate frequency domain vector, wherein the target weight vector is the first weight vector in the target standard frequency domain vector set; According to the second formula, a similarity coefficient between the intermediate frequency domain vector and each candidate standard frequency domain vector is determined, thereby obtaining multiple similarity coefficients, wherein the candidate standard frequency domain vector is a standard frequency domain vector in the target standard frequency domain vector set, and the second formula is: Where SML is the similarity coefficient, MDF(n) is the nth element of the intermediate frequency domain vector, SDF(n) is the nth element of the target standard frequency domain vector, and nmax is the total number of elements in the intermediate frequency domain vector; According to the discharge type of the candidate standard frequency domain vector, the multiple similarity coefficients are respectively added to the corresponding multiple discharge type queues, wherein each discharge type queue corresponds to one discharge type.

5. The method for determining the discharge type of GIS equipment according to claim 4, characterized in that: The construction process of the standard frequency domain vector set includes: Obtaining an intermediate weight vector and a plurality of sample frequency domain vectors, wherein each sample frequency domain vector corresponds to a discharge type; Clustering the plurality of sample frequency domain vectors into a plurality of sample classes as many as the number of discharge types; The discharge type of the majority vector in each sample class is taken as the cluster discharge type; Calculating the class centers of the multiple sample classes respectively to obtain multiple sample class centers; Extracting heterogeneous vectors from each sample class, thereby obtaining a plurality of heterogeneous vectors, wherein the heterogeneous vectors are sample frequency domain vectors whose discharge type is different from the cluster discharge type of the class to which they belong; If the ratio of the number of the plurality of heterogeneous vectors to the number of the plurality of sample frequency domain vectors is greater than the heterogeneous number ratio threshold, the intermediate weight vector is adjusted according to the plurality of heterogeneous vectors, each sample frequency domain vector is weighted by using the adjusted intermediate weight vector, the sample frequency domain vector after weighting is used as the sample frequency domain vector, and the process jumps to the step of clustering the plurality of sample frequency domain vectors into a plurality of sample classes of the number of discharge types; Otherwise, the multiple target centers are used as the multiple standard frequency domain vectors, the intermediate weight vector is used as the first weight vector, and a standard frequency domain vector set is constructed using the first weight vector and the multiple standard frequency domain vectors.

6. The method for determining the discharge type of GIS equipment according to claim 5, characterized in that: The step of adjusting the intermediate weight vector according to the multiple heterogeneous vectors and performing weighting processing on each sample frequency domain vector using the adjusted intermediate weight vector includes: According to the discharge type of each heterogeneous vector, a sample class center is selected from the multiple sample class centers as a target center, thereby obtaining multiple target centers, wherein the cluster discharge type of the source class of the target center is the same as the discharge type of the heterogeneous vector; A weight optimization equation is constructed according to the multiple heterogeneous vectors and the multiple sample class centers, wherein the weight optimization equation is: In the formula, SSDF i (n) is the nth element of the ith heterogeneous vector, CDF i (n) is the nth element of the target center of the i-th heterogeneous vector, and W(n) is the nth element of the intermediate weight vector; According to the weight optimization equation, adjusting the intermediate weight vector; Each sample frequency domain vector is weighted using the adjusted intermediate weight vector.

7. The method for determining the discharge type of GIS equipment according to any one of claims 1 to 6, characterized in that: The determining the probabilities of a plurality of discharge types according to the plurality of discharge type queues, and determining the discharge type of the discharge noise waveform according to the probabilities of the plurality of discharge types, comprises: Calculate the sum of multiple data in each discharge type queue, thereby obtaining multiple queue sums; According to the third formula and the sum of the multiple queues, multiple discharge probabilities are determined, wherein each discharge probability represents the probability of a discharge type, and the third formula is: Where P(k) is the probability of the kth discharge type, R(k) is the queue sum of the kth discharge queue, and cnmax is the total number of discharge types; The discharge type corresponding to the discharge probability with the largest value is used as the discharge type of the discharge noise waveform.

8. A device for determining the discharge type of GIS equipment, characterized in that: Used to implement the method for determining the discharge type of GIS equipment according to any one of claims 1 to 7, the GIS equipment discharge type determination device comprises: A discharge noise waveform acquisition module, used to acquire a discharge noise waveform; A time-frequency domain feature extraction module, used to extract the time-frequency domain features of the discharge noise waveform to obtain a time-frequency domain matrix; A discharge type queue construction module is used to extract multiple frequency domain vectors from the time-frequency domain matrix, and construct multiple discharge type queues according to a standard frequency domain vector set and the multiple frequency domain vectors, wherein the standard frequency domain vector set represents the discharge types corresponding to the multiple standard frequency domain vectors; as well as, The discharge type determination module is used to determine the probabilities of multiple discharge types according to the multiple discharge type queues, and determine the discharge type of the discharge noise waveform according to the probabilities of the multiple discharge types.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method as claimed in any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Method for determining power cable partial discharge defect type based on spectral analysis

    CN105203936A

  • Cable system insulation defect identification method and device, terminal and medium

    CN116975557A

  • Device fault diagnosis method and apparatus, and electronic device and storage medium

    WO2023093177A1